packet: respect devices with LLTX flag in direct xmit

Quite often it can be useful to test with dummy or similar
devices as a blackhole sink for skbs. Such devices are only
equipped with a single txq, but marked as NETIF_F_LLTX as
they do not require locking their internal queues on xmit
(or implement locking themselves). Therefore, rather use
HARD_TX_{UN,}LOCK API, so that NETIF_F_LLTX will be respected.

trafgen mmap/TX_RING example against dummy device with config
foo: { fill(0xff, 64) } results in the following performance
improvements for such scenarios on an ordinary Core i7/2.80GHz:

Before:

 Performance counter stats for 'trafgen -i foo -o du0 -n100000000' (10 runs):

   160,975,944,159 instructions:k            #    0.55  insns per cycle          ( +-  0.09% )
   293,319,390,278 cycles:k                  #    0.000 GHz                      ( +-  0.35% )
       192,501,104 branch-misses:k                                               ( +-  1.63% )
               831 context-switches:k                                            ( +-  9.18% )
                 7 cpu-migrations:k                                              ( +-  7.40% )
            69,382 cache-misses:k            #    0.010 % of all cache refs      ( +-  2.18% )
       671,552,021 cache-references:k                                            ( +-  1.29% )

      22.856401569 seconds time elapsed                                          ( +-  0.33% )

After:

 Performance counter stats for 'trafgen -i foo -o du0 -n100000000' (10 runs):

   133,788,739,692 instructions:k            #    0.92  insns per cycle          ( +-  0.06% )
   145,853,213,256 cycles:k                  #    0.000 GHz                      ( +-  0.17% )
        59,867,100 branch-misses:k                                               ( +-  4.72% )
               384 context-switches:k                                            ( +-  3.76% )
                 6 cpu-migrations:k                                              ( +-  6.28% )
            70,304 cache-misses:k            #    0.077 % of all cache refs      ( +-  1.73% )
        90,879,408 cache-references:k                                            ( +-  1.35% )

      11.719372413 seconds time elapsed                                          ( +-  0.24% )
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/packet/af_packet.c

@@ -243,40 +243,40 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	const struct net_device_ops *ops = dev->netdev_ops;
 	netdev_features_t features;
 	struct netdev_queue *txq;
+	int ret = NETDEV_TX_BUSY;
 	u16 queue_map;
-	int ret;
 
 	if (unlikely(!netif_running(dev) ||
-		     !netif_carrier_ok(dev))) {
-		kfree_skb(skb);
-		return NET_XMIT_DROP;
-	}
+		     !netif_carrier_ok(dev)))
+		goto drop;
 
 	features = netif_skb_features(skb);
 	if (skb_needs_linearize(skb, features) &&
-	    __skb_linearize(skb)) {
-		kfree_skb(skb);
-		return NET_XMIT_DROP;
-	}
+	    __skb_linearize(skb))
+		goto drop;
 
 	queue_map = skb_get_queue_mapping(skb);
 	txq = netdev_get_tx_queue(dev, queue_map);
 
-	__netif_tx_lock_bh(txq);
-	if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
-		ret = NETDEV_TX_BUSY;
-		kfree_skb(skb);
-		goto out;
-	}
+	local_bh_disable();
 
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	if (!netif_xmit_frozen_or_stopped(txq)) {
 		ret = ops->ndo_start_xmit(skb, dev);
-	if (likely(dev_xmit_complete(ret)))
+		if (ret == NETDEV_TX_OK)
 			txq_trans_update(txq);
-	else
+	}
+	HARD_TX_UNLOCK(dev, txq);
+
+	local_bh_enable();
+
+	if (!dev_xmit_complete(ret))
 		kfree_skb(skb);
-out:
-	__netif_tx_unlock_bh(txq);
+
 	return ret;
+drop:
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
 }
 
 static struct net_device *packet_cached_dev_get(struct packet_sock *po)